fascicle 0.17.4 → 0.17.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +21 -0
- package/dist/AGENTS.md +9 -8
- package/dist/{engine-CbVdzplI.js → engine-BTijBDlY.js} +194 -51
- package/dist/engine-BTijBDlY.js.map +1 -0
- package/dist/index.d.ts +149 -147
- package/dist/index.js +2 -2
- package/dist/{invoke-x5SNh9DV.js → invoke-DnmWf8gE.js} +2 -2
- package/dist/{invoke-x5SNh9DV.js.map → invoke-DnmWf8gE.js.map} +1 -1
- package/dist/{leading_system-C23TJ9OQ.js → leading_system-CHSYz0h9.js} +168 -19
- package/dist/leading_system-CHSYz0h9.js.map +1 -0
- package/dist/testing.js +2 -2
- package/package.json +1 -1
- package/dist/engine-CbVdzplI.js.map +0 -1
- package/dist/leading_system-C23TJ9OQ.js.map +0 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,26 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## v0.17.5 — 2026-10-31
|
|
4
|
+
|
|
5
|
+
### Changed
|
|
6
|
+
|
|
7
|
+
- **A 4xx on the `ai_sdk` transport throws the typed error that the native transport throws, and says what to do.** A 401, a 403, a 404, or a 400 reached you as the AI SDK's own `APICallError`, with no Fascicle wording, because the engine's classifier read only a 429, a 5xx, or a network code. So a wrong key or a wrong model id, the first error a new user meets, was the one that said least, and the two transports disagreed on what to catch, since the native one already threw `provider_auth_error` and `provider_error`. Now a 401 throws `provider_auth_error`, and any other 4xx throws `provider_error` with `status` and `body`. Each has the SDK's error as its `cause` and the message that the native transport builds for the status, such as `anthropic authentication failed (401): invalid x-api-key: check providers.anthropic.api_key`. The message takes the provider's text from the response body, so a Bedrock 403 no longer starts with `undefined:`. The `ollama` adapter lifts the status that its package keeps on the error's `cause`, so a missing model says `run ollama pull nope` on this transport too. `provider_auth_error` gains `cause`. A 429, a 5xx, and a network failure retry as they did. Code that read `statusCode` or `responseBody` off the raw error reads `status` and `body` off the typed one now, or the same fields off its `cause`.
|
|
8
|
+
|
|
9
|
+
### Fixed
|
|
10
|
+
|
|
11
|
+
- **A native 401, 403, or 404 says what to check.** The native transport put the provider's text after the status and stopped there, so `anthropic authentication failed (401): invalid x-api-key` never said which key to look at, and `ollama API error 404: model 'nope' not found` never said how to get the model. A 401 now names the key, as in `anthropic authentication failed (401): invalid x-api-key: check providers.anthropic.api_key`. The `ollama` and `lmstudio` providers send no credentials, so a 401 from either says to check that `base_url` reaches the server without a proxy that asks for them. A 403 says that the credentials lack access to this model or endpoint. A 404 says to check the model id against the provider's model list and that `base_url` points at its API, and when Ollama names the model it doesn't have, it says `run ollama pull nope` instead. The provider's text keeps its place and loses only the period it ended on, and any other 4xx reads as it did. Code that matched the old message text has to match the new one.
|
|
12
|
+
- **A provider that can't be reached is named with its URL, and the message says what to check.** A refused or failed connection on the native transport read `ollama native: network failure: fetch failed`, which named neither the address nor the fix, and Node's `fetch failed` doesn't even say whether the host refused, timed out, or doesn't resolve. It reads `ollama could not be reached at http://localhost:11434/api/chat: fetch failed (ECONNREFUSED): check base_url, and that the server is running (ollama serve)` now, with the code that the failure carried and the command to start the server for Ollama alone. The URL keeps only its origin and path, in the lead and wherever the failure's own text repeats it, so credentials or a key in its query never reach a log. On the `ai_sdk` transport the same failure names the same URL, from the SDK's error. A connection that drops after the response began says `ollama connection dropped while reading the response: terminated`, since the request reached the server. Both still retry, and an exhausted one keeps its lead, as in `network after 4 attempts: ollama could not be reached at ...`. Code that matched the old message text has to match the new one.
|
|
13
|
+
- **An empty `api_key`, `base_url`, or `region` names the config key to pass and where its value usually comes from.** A provider built without one threw `anthropic provider requires a non-empty api_key`, which said what was missing but not where it goes, or where its value is usually kept. It reads `anthropic provider requires a non-empty api_key: pass providers.anthropic.api_key to create_engine, usually process.env.ANTHROPIC_API_KEY` now, and `ollama provider requires a non-empty base_url: pass providers.ollama.base_url to create_engine, usually http://localhost:11434`, and the same for `openai`, `google`, `openrouter`, `lmstudio`, and the `region` that `bedrock` needs. The engine still reads no environment variable, so the message says to pass the value, and names the variable only as where it usually lives. Code that matched the old message text has to match the new one.
|
|
14
|
+
- **`claude_cli` start-up failures say what to do.** A missing Claude Code failed with Node's own `spawn claude ENOENT`, an auth failure named its `refresh_command` only in the field, so the message never said to log in, and a timeout said `no stdout within 120000ms` without naming the option that sets it. A missing binary now reads `failed to spawn 'claude': spawn claude ENOENT: install Claude Code, or set providers.claude_cli.binary to where it is`, and a missing sandbox wrapper gets the same lead without that advice. An auth failure ends `: run claude auth login`, and the two timeouts name `providers.claude_cli.startup_timeout_ms` and `providers.claude_cli.stall_timeout_ms`. Code that matched the old message text has to match the new one.
|
|
15
|
+
- **A response that isn't the provider's protocol points at `base_url`.** A body of the wrong shape, such as a payload that isn't a JSON object, a chat completion with no choices or no message, a stream frame or event that isn't JSON, or a stream event with no block index, threw a `provider_error` that said what was wrong and stopped, though the usual cause is a `base_url` that points at something else. Each one ends `: check that base_url points at the <provider> API` now, as the error for a body that isn't JSON already did. A hosted OpenAI or OpenRouter response with no usage adds `or use the lmstudio provider for a self-hosted server`, since a local server that speaks the same API often leaves usage out. A malformed tool call reads as it did, since the model wrote it. Code that matched the old message text has to match the new one.
|
|
16
|
+
- **An Ollama failure on the `ai_sdk` transport retries, and names its address, as it does on the native one.** `ai-sdk-ollama` wraps the `ollama` client's error, which keeps the status on its `cause` and names no URL, and fetch's own error, whose code sits a level further down, so the engine read neither. An Ollama 429 or 5xx failed at once with the daemon's text, and a daemon that wasn't running failed at once as `fetch failed`. The adapter now gives a failure before the stream the URL and the status that the AI SDK's own errors carry, and the engine looks for a network code anywhere down an error's chain of causes. All three retry now, and a daemon that isn't running reads `ollama could not be reached at http://localhost:11434/api/chat: fetch failed (ECONNREFUSED): check base_url, and that the server is running (ollama serve)` on both transports. A connection that drops mid-stream retries as it did, and isn't named as a server that couldn't be reached.
|
|
17
|
+
- **A `base_url` that holds a user name or password is refused when the engine is built, without repeating it.** Node's fetch won't send a request to a URL with credentials in it, and its error names the whole URL, so `http://user:sk-secret@gateway/v1` failed at the first call with the secret in the message, as the AI SDK's raw `TypeError` on the `ai_sdk` transport and inside the network failure's detail on the native one, which retried it as well. No built-in adapter could ever send it, so `create_engine` now throws `engine_config_error` for one, with a scheme or without, before any request: `openai provider's base_url holds a user name or password, which fetch refuses to send: take them out of base_url, and pass the key as providers.openai.api_key`, or for `ollama` and `lmstudio`, which send no credentials, a message that says so. An `@` in a path or a query is left alone, and so is a custom provider's `base_url`.
|
|
18
|
+
|
|
19
|
+
### Internal
|
|
20
|
+
|
|
21
|
+
- **Lesson 6's error table says what the next release prints, and the docs quote the new messages.** The lesson claimed that every message in its table but the last said what to do, which wasn't true of the 401, the network failure, or `spawn claude ENOENT`. Each of those rows now quotes what releases after 0.17.4 print, and the closing paragraph says which messages name the fix and why a 400 passes on the provider's own reason. [troubleshooting.md](./docs/troubleshooting.md#a-provider-could-not-be-reached) gains an entry for a provider that can't be reached, and the auth, `claude_cli`, provider, configuration, and primer pages describe the messages as they read now. The roadmap's Known Issues bullet keeps only the errors that still don't say what to do.
|
|
22
|
+
- **Releases go through the shared `version` plugin, and the roadmap is current to 0.17.4.** The repo's own `/version` skill and `scripts/bump-version.mjs` repeated what the `version` plugin does, and the skill said to draft the release notes from commits, though fix and feature commits here write their entries under `## Unreleased` as they land, so an agent that followed it would have written them twice. `.claude/version.json` now holds the conventions that the script and the skill hard-coded, and `.claude/version.md` keeps what config can't say, such as the `npm-publish` approval that a tag waits on. The roadmap's Shipped list covers 0.17.3 and 0.17.4.
|
|
23
|
+
|
|
3
24
|
## v0.17.4 — 2026-10-30
|
|
4
25
|
|
|
5
26
|
### Changed
|
package/dist/AGENTS.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
This file is for a coding agent (Claude Code, Codex, Cursor, or another) that's
|
|
4
4
|
working in a project which uses the published `fascicle` package. A person who
|
|
5
5
|
is learning Fascicle will usually import it from their `CLAUDE.md`, as
|
|
6
|
-
[lesson 0](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
6
|
+
[lesson 0](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/learn/00-set-up.md) shows. Every shape, rule, and error message below
|
|
7
7
|
was checked against `fascicle` 0.16.3, and against 0.15.0 where the two differ,
|
|
8
8
|
except what's marked 0.17.0 and later, which was checked against 0.17.0. A rule
|
|
9
9
|
that a later release changes says what changed.
|
|
@@ -213,7 +213,8 @@ messages are the real ones.
|
|
|
213
213
|
valid model ID`.
|
|
214
214
|
13. **The engine never reads `process.env`.** Your code reads keys and passes
|
|
215
215
|
them in. Keep keys in `.env` and run with `pnpm exec tsx --env-file=.env`.
|
|
216
|
-
A bad key throws `provider_auth_error
|
|
216
|
+
A bad key throws `provider_auth_error`, whose message names the config key
|
|
217
|
+
to check.
|
|
217
218
|
14. **`create_engine` belongs in one module**, and everything else receives an
|
|
218
219
|
`Engine`. Dispose engines in `finally`.
|
|
219
220
|
15. **Run TypeScript with `tsx`.** Local imports end in `.js` under NodeNext
|
|
@@ -397,11 +398,11 @@ describe('the calculator', () => {
|
|
|
397
398
|
|
|
398
399
|
## Where to Look Next
|
|
399
400
|
|
|
400
|
-
- [blueprint.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
401
|
-
- [leaf-arm-spine.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
401
|
+
- [blueprint.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/blueprint.md) for the layout of a growing app.
|
|
402
|
+
- [leaf-arm-spine.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/leaf-arm-spine.md) for choosing a primitive at each
|
|
402
403
|
layer.
|
|
403
|
-
- [composition.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
404
|
-
- [cookbook.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
404
|
+
- [composition.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/composition.md) for one line on every composer.
|
|
405
|
+
- [cookbook.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/cookbook.md) for worked patterns, including tool loops with
|
|
405
406
|
`define_tool`.
|
|
406
|
-
- [testing.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
407
|
-
- [troubleshooting.md](https://github.com/robmclarty/fascicle/blob/v0.17.
|
|
407
|
+
- [testing.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/testing.md) for the stand-in engines.
|
|
408
|
+
- [troubleshooting.md](https://github.com/robmclarty/fascicle/blob/v0.17.5/docs/troubleshooting.md) for errors and their causes.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { C as validate_schema, D as wait_with_abort, E as compute_backoff, S as format_schema_issues, T as failure_meta, j as aborted_error } from "./core-Bfzt55Fl.js";
|
|
2
2
|
import { n as is_record$1 } from "./records-1HU7mWXf.js";
|
|
3
|
-
import { A as
|
|
3
|
+
import { A as provider_auth_error, C as translate_effort_to_sdk_reasoning, D as incomplete_generation_error, E as engine_disposed_error, F as rate_limit_error, I as schema_validation_error, L as tool_approval_denied_error, M as provider_error, N as provider_not_configured_error, O as model_required_error, P as provider_required_error, R as tool_error, S as resolve_transport, T as engine_config_error, _ as load_optional_peer, a as invoke_http_turn, b as normalize_local_usage, c as network_detail, d as parse_tool_call_arguments, f as protocol_error, g as default_normalize_usage, h as unreachable_message, i as error_body_message, j as provider_capability_error, k as on_chunk_error, l as network_failure, m as split_assistant_parts, n as consume_framed_stream, p as read_dialect_init, r as create_line_splitter, s as map_messages_by_role, t as split_leading_system_run, u as non_retryable_status_error, v as missing_config_error, w as claude_cli_error, x as refuse_credentials_in_base_url, y as missing_peer_error, z as turn_timeout_error } from "./leading_system-CHSYz0h9.js";
|
|
4
4
|
import { join } from "node:path";
|
|
5
5
|
import { mkdtempSync, writeFileSync } from "node:fs";
|
|
6
6
|
import { tmpdir } from "node:os";
|
|
@@ -622,7 +622,7 @@ async function retry_with_policy(fn, policy = DEFAULT_RETRY, abort, on_retry) {
|
|
|
622
622
|
try {
|
|
623
623
|
return await fn(attempt);
|
|
624
624
|
} catch (err) {
|
|
625
|
-
const retryable = classify_retryable(err);
|
|
625
|
+
const retryable = classify_retryable$1(err);
|
|
626
626
|
if (retryable === void 0) throw err;
|
|
627
627
|
attempt += 1;
|
|
628
628
|
if (!is_retryable(retryable.kind, policy)) throw build_left_out_error(err, retryable, attempt, last_rate_limit_after);
|
|
@@ -717,7 +717,7 @@ function read_retryable(err) {
|
|
|
717
717
|
* record names as its `cause`, or the thrown value itself when it is already
|
|
718
718
|
* an `Error`, such as `turn_timeout_error`.
|
|
719
719
|
*/
|
|
720
|
-
function classify_retryable(err) {
|
|
720
|
+
function classify_retryable$1(err) {
|
|
721
721
|
if (err === null || typeof err !== "object") return void 0;
|
|
722
722
|
const retryable = read_retryable(err);
|
|
723
723
|
if (retryable === void 0) return void 0;
|
|
@@ -1159,7 +1159,7 @@ function carries_provider_data(parts) {
|
|
|
1159
1159
|
* `'stop'` finish, so the loop continues the turn.
|
|
1160
1160
|
*/
|
|
1161
1161
|
function parse_messages_response(payload) {
|
|
1162
|
-
if (payload === null || typeof payload !== "object") throw
|
|
1162
|
+
if (payload === null || typeof payload !== "object") throw protocol_error("anthropic", "response payload is not a JSON object");
|
|
1163
1163
|
const { text_parts, tool_calls, parts } = collect_content_blocks(Reflect.get(payload, "content"));
|
|
1164
1164
|
const stop_reason = Reflect.get(payload, "stop_reason");
|
|
1165
1165
|
const result = {
|
|
@@ -1206,7 +1206,7 @@ function stream_event_error(event) {
|
|
|
1206
1206
|
*/
|
|
1207
1207
|
function read_block_index(event) {
|
|
1208
1208
|
const index = Reflect.get(event, "index");
|
|
1209
|
-
if (typeof index !== "number") throw
|
|
1209
|
+
if (typeof index !== "number") throw protocol_error("anthropic", "stream event is missing its block index");
|
|
1210
1210
|
return index;
|
|
1211
1211
|
}
|
|
1212
1212
|
/**
|
|
@@ -1221,7 +1221,7 @@ function parse_stream_event(data) {
|
|
|
1221
1221
|
try {
|
|
1222
1222
|
return JSON.parse(data);
|
|
1223
1223
|
} catch {
|
|
1224
|
-
throw
|
|
1224
|
+
throw protocol_error("anthropic", "stream event is not valid JSON");
|
|
1225
1225
|
}
|
|
1226
1226
|
}
|
|
1227
1227
|
/**
|
|
@@ -1475,7 +1475,7 @@ const SUPPORTED$10 = /* @__PURE__ */ new Set([
|
|
|
1475
1475
|
*/
|
|
1476
1476
|
const create_anthropic_native_adapter = (init) => {
|
|
1477
1477
|
const api_key = typeof init.api_key === "string" ? init.api_key : "";
|
|
1478
|
-
if (api_key.length === 0) throw
|
|
1478
|
+
if (api_key.length === 0) throw missing_config_error("anthropic", "api_key", "process.env.ANTHROPIC_API_KEY");
|
|
1479
1479
|
const base_url = (typeof init.base_url === "string" && init.base_url.length > 0 ? init.base_url : DEFAULT_BASE_URL$2).replace(/\/+$/, "");
|
|
1480
1480
|
return {
|
|
1481
1481
|
kind: "native",
|
|
@@ -1570,7 +1570,7 @@ const create_anthropic_adapter = (init) => {
|
|
|
1570
1570
|
*/
|
|
1571
1571
|
const create_anthropic_ai_sdk_adapter = (init) => {
|
|
1572
1572
|
const api_key = typeof init.api_key === "string" ? init.api_key : "";
|
|
1573
|
-
if (api_key.length === 0) throw
|
|
1573
|
+
if (api_key.length === 0) throw missing_config_error("anthropic", "api_key", "process.env.ANTHROPIC_API_KEY");
|
|
1574
1574
|
const base_url = typeof init.base_url === "string" ? init.base_url : void 0;
|
|
1575
1575
|
return {
|
|
1576
1576
|
kind: "ai_sdk",
|
|
@@ -1833,7 +1833,7 @@ function map_chat_usage(raw, dialect) {
|
|
|
1833
1833
|
input_tokens: 0,
|
|
1834
1834
|
output_tokens: 0
|
|
1835
1835
|
};
|
|
1836
|
-
throw
|
|
1836
|
+
throw protocol_error(dialect.name, "response is missing its usage object", "use the lmstudio provider for a self-hosted server");
|
|
1837
1837
|
}
|
|
1838
1838
|
const totals = {
|
|
1839
1839
|
input_tokens: read_number(raw, "prompt_tokens") ?? 0,
|
|
@@ -1897,12 +1897,12 @@ function parse_tool_call(raw, provider) {
|
|
|
1897
1897
|
* rebuilds this same payload shape from deltas before calling it.
|
|
1898
1898
|
*/
|
|
1899
1899
|
function parse_chat_completion(payload, dialect) {
|
|
1900
|
-
if (payload === null || typeof payload !== "object") throw
|
|
1900
|
+
if (payload === null || typeof payload !== "object") throw protocol_error(dialect.name, "response payload is not a JSON object");
|
|
1901
1901
|
const choices = Reflect.get(payload, "choices");
|
|
1902
1902
|
const choice = Array.isArray(choices) ? choices[0] : void 0;
|
|
1903
|
-
if (choice === null || choice === void 0 || typeof choice !== "object") throw
|
|
1903
|
+
if (choice === null || choice === void 0 || typeof choice !== "object") throw protocol_error(dialect.name, "response has no choices");
|
|
1904
1904
|
const message = Reflect.get(choice, "message");
|
|
1905
|
-
if (message === null || typeof message !== "object") throw
|
|
1905
|
+
if (message === null || typeof message !== "object") throw protocol_error(dialect.name, "response choice has no message");
|
|
1906
1906
|
const content = Reflect.get(message, "content");
|
|
1907
1907
|
const raw_tool_calls = Reflect.get(message, "tool_calls");
|
|
1908
1908
|
const tool_calls = Array.isArray(raw_tool_calls) ? raw_tool_calls.map((entry) => parse_tool_call(entry, dialect.name)) : [];
|
|
@@ -2156,7 +2156,7 @@ function create_chat_stream_aggregator(dialect, step_index, dispatch) {
|
|
|
2156
2156
|
try {
|
|
2157
2157
|
frame = JSON.parse(data);
|
|
2158
2158
|
} catch {
|
|
2159
|
-
throw
|
|
2159
|
+
throw protocol_error(dialect.name, "stream frame is not valid JSON");
|
|
2160
2160
|
}
|
|
2161
2161
|
if (frame === null || typeof frame !== "object") return;
|
|
2162
2162
|
const error = Reflect.get(frame, "error");
|
|
@@ -2224,7 +2224,7 @@ const SUPPORTED$8 = /* @__PURE__ */ new Set([
|
|
|
2224
2224
|
* the mappers above.
|
|
2225
2225
|
*/
|
|
2226
2226
|
const create_openai_compatible_adapter = (dialect) => {
|
|
2227
|
-
if (dialect.auth.kind === "bearer" && dialect.auth.api_key.length === 0) throw
|
|
2227
|
+
if (dialect.auth.kind === "bearer" && dialect.auth.api_key.length === 0) throw missing_config_error(dialect.name, "api_key", `process.env.${dialect.name.toUpperCase()}_API_KEY`);
|
|
2228
2228
|
const base_url = dialect.base_url.replace(/\/+$/, "");
|
|
2229
2229
|
const headers = {
|
|
2230
2230
|
"content-type": "application/json",
|
|
@@ -2285,7 +2285,7 @@ const create_openai_adapter = (init) => {
|
|
|
2285
2285
|
* `max_completion_tokens` token-limit field, and strict usage (a hosted API
|
|
2286
2286
|
* omitting usage is a broken response, not a local-runtime quirk). The
|
|
2287
2287
|
* empty-api_key guard rides on the core, which throws the same
|
|
2288
|
-
*
|
|
2288
|
+
* engine_config_error as the ai_sdk branch, naming `OPENAI_API_KEY`.
|
|
2289
2289
|
*/
|
|
2290
2290
|
const create_openai_native_adapter = (init) => {
|
|
2291
2291
|
const { api_key, base_url } = read_dialect_init(init, DEFAULT_BASE_URL$1);
|
|
@@ -2312,7 +2312,7 @@ const create_openai_native_adapter = (init) => {
|
|
|
2312
2312
|
*/
|
|
2313
2313
|
const create_openai_ai_sdk_adapter = (init) => {
|
|
2314
2314
|
const api_key = typeof init.api_key === "string" ? init.api_key : "";
|
|
2315
|
-
if (api_key.length === 0) throw
|
|
2315
|
+
if (api_key.length === 0) throw missing_config_error("openai", "api_key", "process.env.OPENAI_API_KEY");
|
|
2316
2316
|
const base_url = typeof init.base_url === "string" ? init.base_url : void 0;
|
|
2317
2317
|
const organization = typeof init["organization"] === "string" ? init["organization"] : void 0;
|
|
2318
2318
|
return {
|
|
@@ -2353,7 +2353,7 @@ const SUPPORTED$6 = /* @__PURE__ */ new Set([
|
|
|
2353
2353
|
*/
|
|
2354
2354
|
const create_google_adapter = (init) => {
|
|
2355
2355
|
const api_key = typeof init.api_key === "string" ? init.api_key : "";
|
|
2356
|
-
if (api_key.length === 0) throw
|
|
2356
|
+
if (api_key.length === 0) throw missing_config_error("google", "api_key", "process.env.GOOGLE_API_KEY");
|
|
2357
2357
|
const base_url = typeof init.base_url === "string" ? init.base_url : void 0;
|
|
2358
2358
|
return {
|
|
2359
2359
|
kind: "ai_sdk",
|
|
@@ -2541,9 +2541,9 @@ function parse_ollama_tool_call(raw, ordinal, step_index) {
|
|
|
2541
2541
|
* its frames before calling it.
|
|
2542
2542
|
*/
|
|
2543
2543
|
function parse_ollama_chat(payload, step_index) {
|
|
2544
|
-
if (payload === null || typeof payload !== "object") throw
|
|
2544
|
+
if (payload === null || typeof payload !== "object") throw protocol_error("ollama", "response payload is not a JSON object");
|
|
2545
2545
|
const message = Reflect.get(payload, "message");
|
|
2546
|
-
if (message === null || message === void 0 || typeof message !== "object") throw
|
|
2546
|
+
if (message === null || message === void 0 || typeof message !== "object") throw protocol_error("ollama", "response has no message");
|
|
2547
2547
|
const content = Reflect.get(message, "content");
|
|
2548
2548
|
const raw_tool_calls = Reflect.get(message, "tool_calls");
|
|
2549
2549
|
const tool_calls = Array.isArray(raw_tool_calls) ? raw_tool_calls.map((entry, ordinal) => parse_ollama_tool_call(entry, ordinal, step_index)) : [];
|
|
@@ -2636,7 +2636,7 @@ function create_ollama_stream_aggregator(step_index, dispatch) {
|
|
|
2636
2636
|
try {
|
|
2637
2637
|
frame = JSON.parse(line);
|
|
2638
2638
|
} catch {
|
|
2639
|
-
throw
|
|
2639
|
+
throw protocol_error("ollama", "stream frame is not valid JSON");
|
|
2640
2640
|
}
|
|
2641
2641
|
if (frame === null || typeof frame !== "object") return;
|
|
2642
2642
|
const error = Reflect.get(frame, "error");
|
|
@@ -2701,7 +2701,7 @@ const SUPPORTED$5 = /* @__PURE__ */ new Set([
|
|
|
2701
2701
|
*/
|
|
2702
2702
|
const create_ollama_native_adapter = (init) => {
|
|
2703
2703
|
const raw_base_url = typeof init.base_url === "string" ? init.base_url : "";
|
|
2704
|
-
if (raw_base_url.length === 0) throw
|
|
2704
|
+
if (raw_base_url.length === 0) throw missing_config_error("ollama", "base_url", "http://localhost:11434");
|
|
2705
2705
|
const base_url = raw_base_url.replace(/\/+$/, "");
|
|
2706
2706
|
return {
|
|
2707
2707
|
kind: "native",
|
|
@@ -2723,6 +2723,44 @@ const create_ollama_native_adapter = (init) => {
|
|
|
2723
2723
|
//#endregion
|
|
2724
2724
|
//#region src/engine/providers/ollama.ts
|
|
2725
2725
|
/**
|
|
2726
|
+
* Give a failure that `ai-sdk-ollama` raised the `url` and `statusCode` that
|
|
2727
|
+
* the AI SDK's own errors carry. The package wraps the `ollama` client's
|
|
2728
|
+
* error, which keeps the status as `status_code` on the `cause`, and names
|
|
2729
|
+
* no URL, so without these the engine can't retry a 429 or a 5xx, and can't
|
|
2730
|
+
* say which address didn't answer.
|
|
2731
|
+
*/
|
|
2732
|
+
function add_request_facts(err, url) {
|
|
2733
|
+
if (err === null || typeof err !== "object") return;
|
|
2734
|
+
const cause = Reflect.get(err, "cause");
|
|
2735
|
+
const status = cause !== null && typeof cause === "object" ? Reflect.get(cause, "status_code") : void 0;
|
|
2736
|
+
Object.assign(err, typeof status === "number" ? {
|
|
2737
|
+
url,
|
|
2738
|
+
statusCode: status
|
|
2739
|
+
} : { url });
|
|
2740
|
+
}
|
|
2741
|
+
/**
|
|
2742
|
+
* The package's model, with a `doStream` whose failures carry the request's
|
|
2743
|
+
* URL and status (see add_request_facts), and everything else read through
|
|
2744
|
+
* to the model itself. Only `doStream` is wrapped, since every engine turn
|
|
2745
|
+
* streams, and only its own rejection, which is a failure before the stream
|
|
2746
|
+
* began. A connection that drops mid-stream reaches the stream as it is, so
|
|
2747
|
+
* it's never named as a server that couldn't be reached.
|
|
2748
|
+
*/
|
|
2749
|
+
function with_request_facts(model, url) {
|
|
2750
|
+
if (model === null || typeof model !== "object") return model;
|
|
2751
|
+
const do_stream = Reflect.get(model, "doStream");
|
|
2752
|
+
if (typeof do_stream !== "function") return model;
|
|
2753
|
+
const stream = async (...args) => {
|
|
2754
|
+
try {
|
|
2755
|
+
return await Reflect.apply(do_stream, model, args);
|
|
2756
|
+
} catch (err) {
|
|
2757
|
+
add_request_facts(err, url);
|
|
2758
|
+
throw err;
|
|
2759
|
+
}
|
|
2760
|
+
};
|
|
2761
|
+
return Object.create(model, { doStream: { value: stream } });
|
|
2762
|
+
}
|
|
2763
|
+
/**
|
|
2726
2764
|
* Ollama has no reasoning-effort control on this transport, so every
|
|
2727
2765
|
* non-`none` level is reported as ignored and no provider option is emitted.
|
|
2728
2766
|
*/
|
|
@@ -2755,16 +2793,18 @@ const create_ollama_adapter = (init) => {
|
|
|
2755
2793
|
};
|
|
2756
2794
|
/**
|
|
2757
2795
|
* Build the Ollama ai_sdk adapter: validates the required base_url and
|
|
2758
|
-
* lazily loads ai-sdk-ollama to build models
|
|
2796
|
+
* lazily loads ai-sdk-ollama to build models, whose failures before a stream
|
|
2797
|
+
* begins carry the chat URL and the status (see with_request_facts).
|
|
2759
2798
|
*/
|
|
2760
2799
|
const create_ollama_ai_sdk_adapter = (init) => {
|
|
2761
2800
|
const base_url = typeof init.base_url === "string" ? init.base_url : "";
|
|
2762
|
-
if (base_url.length === 0) throw
|
|
2801
|
+
if (base_url.length === 0) throw missing_config_error("ollama", "base_url", "http://localhost:11434");
|
|
2802
|
+
const chat_url = `${base_url.replace(/\/+$/, "")}/api/chat`;
|
|
2763
2803
|
return {
|
|
2764
2804
|
kind: "ai_sdk",
|
|
2765
2805
|
name: "ollama",
|
|
2766
2806
|
async build_model(model_id) {
|
|
2767
|
-
return (await load_optional_peer("ai-sdk-ollama")).createOllama({ baseURL: base_url })(model_id);
|
|
2807
|
+
return with_request_facts((await load_optional_peer("ai-sdk-ollama")).createOllama({ baseURL: base_url })(model_id), chat_url);
|
|
2768
2808
|
},
|
|
2769
2809
|
translate_effort: translate_ollama_effort,
|
|
2770
2810
|
normalize_usage: normalize_ollama_usage,
|
|
@@ -2812,7 +2852,7 @@ const create_lmstudio_adapter = (init) => {
|
|
|
2812
2852
|
*/
|
|
2813
2853
|
const create_lmstudio_native_adapter = (init) => {
|
|
2814
2854
|
const base_url = typeof init.base_url === "string" ? init.base_url : "";
|
|
2815
|
-
if (base_url.length === 0) throw
|
|
2855
|
+
if (base_url.length === 0) throw missing_config_error("lmstudio", "base_url", "http://localhost:1234/v1");
|
|
2816
2856
|
return create_openai_compatible_adapter({
|
|
2817
2857
|
name: "lmstudio",
|
|
2818
2858
|
base_url,
|
|
@@ -2830,7 +2870,7 @@ const create_lmstudio_native_adapter = (init) => {
|
|
|
2830
2870
|
*/
|
|
2831
2871
|
const create_lmstudio_ai_sdk_adapter = (init) => {
|
|
2832
2872
|
const base_url = typeof init.base_url === "string" ? init.base_url : "";
|
|
2833
|
-
if (base_url.length === 0) throw
|
|
2873
|
+
if (base_url.length === 0) throw missing_config_error("lmstudio", "base_url", "http://localhost:1234/v1");
|
|
2834
2874
|
return {
|
|
2835
2875
|
kind: "ai_sdk",
|
|
2836
2876
|
name: "lmstudio",
|
|
@@ -2902,7 +2942,7 @@ const create_openrouter_adapter = (init) => {
|
|
|
2902
2942
|
* the cost OpenRouter reports on every response, and caching only when the
|
|
2903
2943
|
* call or the engine asks for it, since only Claude models take the field.
|
|
2904
2944
|
* The empty-api_key guard rides on the core, which throws the same
|
|
2905
|
-
*
|
|
2945
|
+
* engine_config_error as the ai_sdk branch, naming `OPENROUTER_API_KEY`.
|
|
2906
2946
|
*/
|
|
2907
2947
|
const create_openrouter_native_adapter = (init) => {
|
|
2908
2948
|
const { api_key, base_url } = read_dialect_init(init, DEFAULT_BASE_URL);
|
|
@@ -2935,7 +2975,7 @@ const create_openrouter_native_adapter = (init) => {
|
|
|
2935
2975
|
*/
|
|
2936
2976
|
const create_openrouter_ai_sdk_adapter = (init) => {
|
|
2937
2977
|
const api_key = typeof init.api_key === "string" ? init.api_key : "";
|
|
2938
|
-
if (api_key.length === 0) throw
|
|
2978
|
+
if (api_key.length === 0) throw missing_config_error("openrouter", "api_key", "process.env.OPENROUTER_API_KEY");
|
|
2939
2979
|
const base_url = typeof init.base_url === "string" ? init.base_url : void 0;
|
|
2940
2980
|
const http_referer = typeof init["http_referer"] === "string" ? init["http_referer"] : void 0;
|
|
2941
2981
|
const x_title = typeof init["x_title"] === "string" ? init["x_title"] : void 0;
|
|
@@ -2981,7 +3021,7 @@ function read_string(init, key) {
|
|
|
2981
3021
|
/** Pull the static fields off init, rejecting a missing or non-string region. */
|
|
2982
3022
|
function read_static_credentials(init) {
|
|
2983
3023
|
const region = read_string(init, "region") ?? "";
|
|
2984
|
-
if (region.length === 0) throw
|
|
3024
|
+
if (region.length === 0) throw missing_config_error("bedrock", "region", "process.env.AWS_REGION");
|
|
2985
3025
|
return {
|
|
2986
3026
|
region,
|
|
2987
3027
|
api_key: read_string(init, "api_key"),
|
|
@@ -3076,6 +3116,11 @@ const CLI_AUTH_ERROR_PATTERNS = Object.freeze([
|
|
|
3076
3116
|
"oauth token has expired",
|
|
3077
3117
|
"invalid_api_key"
|
|
3078
3118
|
]);
|
|
3119
|
+
/**
|
|
3120
|
+
* The command that logs the CLI in again, which an auth failure's message
|
|
3121
|
+
* names and its `refresh_command` carries.
|
|
3122
|
+
*/
|
|
3123
|
+
const CLI_REFRESH_COMMAND = "claude auth login";
|
|
3079
3124
|
const DEFAULT_SETTING_SOURCES = Object.freeze(["project", "local"]);
|
|
3080
3125
|
//#endregion
|
|
3081
3126
|
//#region src/engine/providers/claude_cli/auth.ts
|
|
@@ -3392,6 +3437,15 @@ function write_greywall_settings(sandbox) {
|
|
|
3392
3437
|
* `shell: false` via argv array form; no value is string-interpolated into
|
|
3393
3438
|
* argv.
|
|
3394
3439
|
*/
|
|
3440
|
+
/**
|
|
3441
|
+
* The message for a command that couldn't be started: the command, Node's
|
|
3442
|
+
* reason, and, when the claude binary itself is missing, how to install it
|
|
3443
|
+
* or point at it. A sandbox wrapper that's missing gets no such advice,
|
|
3444
|
+
* since installing Claude Code won't help it.
|
|
3445
|
+
*/
|
|
3446
|
+
function spawn_failure_message(cmd, reason, detail) {
|
|
3447
|
+
return `failed to spawn '${cmd}': ${detail}${reason === "binary_not_found" ? ": install Claude Code, or set providers.claude_cli.binary to where it is" : ""}`;
|
|
3448
|
+
}
|
|
3395
3449
|
const ALL_REGISTRIES = /* @__PURE__ */ new Set();
|
|
3396
3450
|
let exit_handler_installed = false;
|
|
3397
3451
|
/**
|
|
@@ -3450,7 +3504,7 @@ function create_spawn_runtime() {
|
|
|
3450
3504
|
child = spawn(args.cmd, [...args.argv], spawn_opts);
|
|
3451
3505
|
} catch (err) {
|
|
3452
3506
|
const message = err instanceof Error ? err.message : String(err);
|
|
3453
|
-
throw new claude_cli_error(spawn_failure_reason,
|
|
3507
|
+
throw new claude_cli_error(spawn_failure_reason, spawn_failure_message(args.cmd, spawn_failure_reason, message));
|
|
3454
3508
|
}
|
|
3455
3509
|
live_children.add(child);
|
|
3456
3510
|
let spawn_error;
|
|
@@ -3492,14 +3546,14 @@ function create_spawn_runtime() {
|
|
|
3492
3546
|
};
|
|
3493
3547
|
if (args.startup_timeout_ms > 0) startup_timer = setTimeout(() => {
|
|
3494
3548
|
if (first_stdout_byte_seen) return;
|
|
3495
|
-
startup_error = new claude_cli_error("startup_timeout", `no stdout within ${String(args.startup_timeout_ms)}ms`);
|
|
3549
|
+
startup_error = new claude_cli_error("startup_timeout", `no stdout within ${String(args.startup_timeout_ms)}ms: raise providers.claude_cli.startup_timeout_ms if Claude Code needs longer to start`);
|
|
3496
3550
|
escalate("timeout");
|
|
3497
3551
|
}, args.startup_timeout_ms);
|
|
3498
3552
|
const arm_stall_timer = () => {
|
|
3499
3553
|
if (args.stall_timeout_ms <= 0) return;
|
|
3500
3554
|
clearTimeout(stall_timer);
|
|
3501
3555
|
stall_timer = setTimeout(() => {
|
|
3502
|
-
stall_error = new claude_cli_error("stall_timeout", `no stdout for ${String(args.stall_timeout_ms)}ms`);
|
|
3556
|
+
stall_error = new claude_cli_error("stall_timeout", `no stdout for ${String(args.stall_timeout_ms)}ms: raise providers.claude_cli.stall_timeout_ms if the model's pauses run longer`);
|
|
3503
3557
|
escalate("timeout");
|
|
3504
3558
|
}, args.stall_timeout_ms);
|
|
3505
3559
|
};
|
|
@@ -3543,10 +3597,7 @@ function create_spawn_runtime() {
|
|
|
3543
3597
|
stdout_lines,
|
|
3544
3598
|
wait_close: async () => {
|
|
3545
3599
|
const outcome = await close_promise;
|
|
3546
|
-
if (spawn_error !== void 0)
|
|
3547
|
-
const message = spawn_error.message;
|
|
3548
|
-
throw new claude_cli_error(spawn_failure_reason, message);
|
|
3549
|
-
}
|
|
3600
|
+
if (spawn_error !== void 0) throw new claude_cli_error(spawn_failure_reason, spawn_failure_message(args.cmd, spawn_failure_reason, spawn_error.message));
|
|
3550
3601
|
if (startup_error !== void 0) throw startup_error;
|
|
3551
3602
|
if (stall_error !== void 0) throw stall_error;
|
|
3552
3603
|
if (terminate_reason === "abort") throw new aborted_error("aborted", { reason: args.abort?.reason });
|
|
@@ -5073,7 +5124,10 @@ function classify_close_error(code, signal, stderr, parsed) {
|
|
|
5073
5124
|
const snippet = stderr.slice(0, 512);
|
|
5074
5125
|
const reported = parsed?.is_error === true ? parsed.final_text.slice(0, 512) : "";
|
|
5075
5126
|
const detail = snippet.length > 0 ? snippet : reported;
|
|
5076
|
-
if (stderr_is_auth_failure(stderr) || parsed?.api_error === "authentication_failed")
|
|
5127
|
+
if (stderr_is_auth_failure(stderr) || parsed?.api_error === "authentication_failed") {
|
|
5128
|
+
const reason = detail.length > 0 ? `${detail}: ` : "";
|
|
5129
|
+
return new provider_auth_error(PROVIDER_NAME, `claude CLI reported an auth failure: ${reason}run ${CLI_REFRESH_COMMAND}`, { refresh_command: CLI_REFRESH_COMMAND });
|
|
5130
|
+
}
|
|
5077
5131
|
const sandboxed_binary = BWRAP_EXEC_MISSING.exec(stderr)?.[1];
|
|
5078
5132
|
if (sandboxed_binary !== void 0) return new claude_cli_error("binary_not_found", `bwrap ran but found no claude binary at '${sandboxed_binary}' inside its sandbox, which binds only /usr, /bin, /lib, /lib64, and additional_write_paths: ${snippet}`, { stderr_snippet: snippet });
|
|
5079
5133
|
if (/bwrap|greywall|sandbox/i.test(stderr) && /not found|no such file|enoent/i.test(stderr)) return new claude_cli_error("sandbox_unavailable", `sandbox binary unavailable: ${snippet}`, { stderr_snippet: snippet });
|
|
@@ -7370,12 +7424,29 @@ function has_network_code(value) {
|
|
|
7370
7424
|
return typeof code === "string" && NETWORK_ERROR_CODES.has(code);
|
|
7371
7425
|
}
|
|
7372
7426
|
/**
|
|
7373
|
-
*
|
|
7374
|
-
*
|
|
7375
|
-
*
|
|
7427
|
+
* True when `err`, or any error down its chain of `cause`s, carries a known
|
|
7428
|
+
* network error code. The AI SDK wraps a failed fetch in an `APICallError`
|
|
7429
|
+
* whose `cause` holds undici's code, and `ai-sdk-ollama` wraps fetch's own
|
|
7430
|
+
* `TypeError`, whose `cause` holds it, one level further down. A chain that
|
|
7431
|
+
* leads back to an error already seen ends there.
|
|
7432
|
+
*/
|
|
7433
|
+
function has_network_code_in_chain(err) {
|
|
7434
|
+
const seen = /* @__PURE__ */ new Set();
|
|
7435
|
+
let value = err;
|
|
7436
|
+
while (value !== null && typeof value === "object" && !seen.has(value)) {
|
|
7437
|
+
if (has_network_code(value)) return true;
|
|
7438
|
+
seen.add(value);
|
|
7439
|
+
value = Reflect.get(value, "cause");
|
|
7440
|
+
}
|
|
7441
|
+
return false;
|
|
7442
|
+
}
|
|
7443
|
+
/**
|
|
7444
|
+
* Build the `network` classification when the error or an error down its
|
|
7445
|
+
* chain of `cause`s carries a known network error code, or `undefined` when
|
|
7446
|
+
* none does.
|
|
7376
7447
|
*/
|
|
7377
7448
|
function classify_network_error(err) {
|
|
7378
|
-
if (!
|
|
7449
|
+
if (!has_network_code_in_chain(err)) return void 0;
|
|
7379
7450
|
return with_error_source(err, { kind: "network" });
|
|
7380
7451
|
}
|
|
7381
7452
|
/**
|
|
@@ -7388,17 +7459,81 @@ function classify_network_error(err) {
|
|
|
7388
7459
|
* and the body off `responseBody` or `body` when present, and a known network
|
|
7389
7460
|
* error code (`ECONNRESET`, `ETIMEDOUT`,
|
|
7390
7461
|
* `ENOTFOUND`, `ECONNREFUSED`, or undici's `UND_ERR_HEADERS_TIMEOUT`,
|
|
7391
|
-
* `UND_ERR_BODY_TIMEOUT`, and `UND_ERR_SOCKET`), on the error or
|
|
7392
|
-
* `cause
|
|
7393
|
-
* which `retry_with_policy` treats as non-retryable.
|
|
7462
|
+
* `UND_ERR_BODY_TIMEOUT`, and `UND_ERR_SOCKET`), on the error or anywhere
|
|
7463
|
+
* down its chain of `cause`s, becomes `network`. Anything else passes through unclassified,
|
|
7464
|
+
* which `retry_with_policy` treats as non-retryable. The ai_sdk transport
|
|
7465
|
+
* runs it inside classify_ai_sdk_error, which also types any other 4xx.
|
|
7394
7466
|
*/
|
|
7395
7467
|
function classify_provider_error(err) {
|
|
7396
7468
|
if (err === null || typeof err !== "object") return err;
|
|
7397
7469
|
if (has_retry_kind(err)) return err;
|
|
7470
|
+
return classify_retryable(err) ?? err;
|
|
7471
|
+
}
|
|
7472
|
+
/**
|
|
7473
|
+
* The record for a failure that retries, a 429, a 5xx, or a known network
|
|
7474
|
+
* code, or `undefined` for any other.
|
|
7475
|
+
*/
|
|
7476
|
+
function classify_retryable(err) {
|
|
7398
7477
|
const status = resolve_error_status(err);
|
|
7399
7478
|
if (status === 429) return classify_status(err, "rate_limit", status);
|
|
7400
7479
|
if (status !== void 0 && status >= 500 && status < 600) return classify_status(err, "provider_5xx", status);
|
|
7401
|
-
return classify_network_error(err)
|
|
7480
|
+
return classify_network_error(err);
|
|
7481
|
+
}
|
|
7482
|
+
/**
|
|
7483
|
+
* True when `err` carries any string `kind`, the mark of a Fascicle typed
|
|
7484
|
+
* error and of every record classify_provider_error builds.
|
|
7485
|
+
*/
|
|
7486
|
+
function has_kind(err) {
|
|
7487
|
+
return typeof Reflect.get(err, "kind") === "string";
|
|
7488
|
+
}
|
|
7489
|
+
/**
|
|
7490
|
+
* The typed error for an AI SDK failure whose status says a retry won't
|
|
7491
|
+
* help, any 4xx but the 429 that classify_provider_error claims first, or
|
|
7492
|
+
* `undefined` when the failure carries no such status. It's the error the
|
|
7493
|
+
* native transport throws for the same status, with the SDK's error as its
|
|
7494
|
+
* `cause` and the provider's own message read off the body when the SDK
|
|
7495
|
+
* attached one.
|
|
7496
|
+
*/
|
|
7497
|
+
function classify_client_status(provider, err) {
|
|
7498
|
+
const status = resolve_error_status(err);
|
|
7499
|
+
if (status === void 0 || status < 400 || status > 499) return void 0;
|
|
7500
|
+
return non_retryable_status_error(provider, status, provider_message(err) ?? "(no detail)", {
|
|
7501
|
+
body: response_body(err),
|
|
7502
|
+
cause: err
|
|
7503
|
+
});
|
|
7504
|
+
}
|
|
7505
|
+
/**
|
|
7506
|
+
* A network record whose message names the URL that the SDK couldn't reach,
|
|
7507
|
+
* in the words the native transport uses, when the SDK's error carries its
|
|
7508
|
+
* `url`, and the record as it is otherwise. The detail comes from the SDK
|
|
7509
|
+
* error's `cause`, the failure that fetch threw, when it has one, since the
|
|
7510
|
+
* SDK's own message only puts `Cannot connect to API:` in front of it.
|
|
7511
|
+
*/
|
|
7512
|
+
function name_unreachable_url(provider, err, record) {
|
|
7513
|
+
const url = Reflect.get(err, "url");
|
|
7514
|
+
if (record["kind"] !== "network" || typeof url !== "string") return record;
|
|
7515
|
+
const detail = network_detail(Reflect.get(err, "cause") ?? err);
|
|
7516
|
+
return {
|
|
7517
|
+
...record,
|
|
7518
|
+
message: unreachable_message(provider, url, detail)
|
|
7519
|
+
};
|
|
7520
|
+
}
|
|
7521
|
+
/**
|
|
7522
|
+
* Build the classifier for one ai_sdk provider. A 429, a 5xx, or a network
|
|
7523
|
+
* failure becomes the record classify_provider_error builds for it, with a
|
|
7524
|
+
* network failure's message naming the URL, and any other 4xx becomes the
|
|
7525
|
+
* typed error the native transport throws, closed over `provider` so that
|
|
7526
|
+
* its message can name the config key to check. Anything already classified
|
|
7527
|
+
* or typed, and anything with no status, passes through as it is.
|
|
7528
|
+
*/
|
|
7529
|
+
function classify_ai_sdk_error(provider) {
|
|
7530
|
+
return (err) => {
|
|
7531
|
+
if (err === null || typeof err !== "object" || has_retry_kind(err)) return err;
|
|
7532
|
+
const record = classify_retryable(err);
|
|
7533
|
+
if (record !== void 0) return name_unreachable_url(provider, err, record);
|
|
7534
|
+
if (has_kind(err)) return err;
|
|
7535
|
+
return classify_client_status(provider, err) ?? err;
|
|
7536
|
+
};
|
|
7402
7537
|
}
|
|
7403
7538
|
/**
|
|
7404
7539
|
* Compose the per-attempt turn signal: the user's abort OR'd with a fresh
|
|
@@ -7510,9 +7645,11 @@ function build_step_timing(started_at, stamp) {
|
|
|
7510
7645
|
* turn streams; this builder owns only retry and the first-chunk stamp, which
|
|
7511
7646
|
* it clears as each attempt starts, and which both makes a failure after a
|
|
7512
7647
|
* chunk reached a consumer a non-retryable interruption and doubles as
|
|
7513
|
-
* StepTiming.first_chunk_ms.
|
|
7648
|
+
* StepTiming.first_chunk_ms. Its classifier is classify_ai_sdk_error, closed
|
|
7649
|
+
* over the call's provider.
|
|
7514
7650
|
*/
|
|
7515
7651
|
function build_ai_sdk_invoke(cfg) {
|
|
7652
|
+
const classify = classify_ai_sdk_error(cfg.provider);
|
|
7516
7653
|
return async (args) => {
|
|
7517
7654
|
const stamp = create_first_chunk_stamp();
|
|
7518
7655
|
const call_once = (turn_abort) => {
|
|
@@ -7524,7 +7661,7 @@ function build_ai_sdk_invoke(cfg) {
|
|
|
7524
7661
|
observe_chunk: stamp.observe
|
|
7525
7662
|
});
|
|
7526
7663
|
};
|
|
7527
|
-
return await retry_turn(call_once, args, stamp, cfg.retry_policy,
|
|
7664
|
+
return await retry_turn(call_once, args, stamp, cfg.retry_policy, classify, cfg.turn_timeout_ms, cfg.trajectory, cfg.on_chunk_provided);
|
|
7528
7665
|
};
|
|
7529
7666
|
}
|
|
7530
7667
|
/**
|
|
@@ -7820,12 +7957,13 @@ async function build_ai_sdk_transport(cfg) {
|
|
|
7820
7957
|
const provider_options = combined_provider_options !== void 0 && Object.keys(combined_provider_options).length > 0 ? combined_provider_options : void 0;
|
|
7821
7958
|
let ai_sdk_invoke_mod;
|
|
7822
7959
|
try {
|
|
7823
|
-
ai_sdk_invoke_mod = await import("./invoke-
|
|
7960
|
+
ai_sdk_invoke_mod = await import("./invoke-DnmWf8gE.js");
|
|
7824
7961
|
} catch (err) {
|
|
7825
7962
|
throw missing_peer_error("ai", err);
|
|
7826
7963
|
}
|
|
7827
7964
|
const { create_ai_sdk_turn } = ai_sdk_invoke_mod;
|
|
7828
7965
|
return build_ai_sdk_invoke({
|
|
7966
|
+
provider: cfg.target.provider,
|
|
7829
7967
|
invoke_turn: create_ai_sdk_turn({
|
|
7830
7968
|
adapter,
|
|
7831
7969
|
model_id: cfg.target.model_id,
|
|
@@ -8290,7 +8428,9 @@ function aggregate_cost(steps, provider) {
|
|
|
8290
8428
|
* Each factory validates its init value synchronously, so a bad credential
|
|
8291
8429
|
* throws here at construction time rather than later; loading the
|
|
8292
8430
|
* underlying SDK is deferred until the first `generate` call. Throws if
|
|
8293
|
-
* `custom_providers` tries to shadow a built-in provider name
|
|
8431
|
+
* `custom_providers` tries to shadow a built-in provider name, or if a
|
|
8432
|
+
* built-in provider's `base_url` holds credentials, which no built-in
|
|
8433
|
+
* adapter could send.
|
|
8294
8434
|
*/
|
|
8295
8435
|
function build_provider_adapters(providers, custom_providers) {
|
|
8296
8436
|
if (custom_providers !== void 0) {
|
|
@@ -8300,7 +8440,10 @@ function build_provider_adapters(providers, custom_providers) {
|
|
|
8300
8440
|
const adapters = /* @__PURE__ */ new Map();
|
|
8301
8441
|
for (const [name, init] of Object.entries(providers)) {
|
|
8302
8442
|
if (init === void 0) continue;
|
|
8303
|
-
const
|
|
8443
|
+
const custom = custom_providers !== void 0 && Object.hasOwn(custom_providers, name) ? custom_providers[name] : void 0;
|
|
8444
|
+
const factory = custom ?? get_provider_factory(name);
|
|
8445
|
+
if (custom === void 0) refuse_credentials_in_base_url(name, init);
|
|
8446
|
+
const adapter = factory(init);
|
|
8304
8447
|
adapters.set(name, adapter);
|
|
8305
8448
|
}
|
|
8306
8449
|
return adapters;
|
|
@@ -8457,4 +8600,4 @@ function create_engine(config) {
|
|
|
8457
8600
|
//#endregion
|
|
8458
8601
|
export { to_json_schema as n, create_engine as t };
|
|
8459
8602
|
|
|
8460
|
-
//# sourceMappingURL=engine-
|
|
8603
|
+
//# sourceMappingURL=engine-BTijBDlY.js.map
|